Low coherence imaging quality evaluation method, device and electronic equipment

Abstract

This application discloses a low-coherence imaging quality evaluation method, device, and electronic device, relating to the field of laser welding monitoring technology. The method includes: acquiring point cloud data related to a keyhole during laser welding, and obtaining a peripheral point cloud projection of the keyhole based on the point cloud data; performing a keyhole region fitting process multiple times to determine the keyhole region based on the fitting parameters obtained during each fitting process; wherein, during each fitting process, a coordinate system is constructed based on the peripheral point cloud projection and gridded according to a preset scale, and the fitting parameters of the keyhole region are determined based on the grid parameters of each grid; the preset scale varies between fitting processes; and an imaging quality evaluation result is determined based on the point cloud data within the keyhole region and the area of ​​the keyhole region. This method thereby evaluates the accuracy of key depth information collected via optical low-coherence imaging, providing a prerequisite for online key depth monitoring during laser welding.

Description

Technical Field

[0001] The present application relates to the field of laser welding monitoring technology, and in particular to a low-coherence imaging quality evaluation method, device and electronic equipment. Background Art

[0002] Laser welding is a high-precision welding method that uses a high-energy-density laser beam as a heat source. During the laser welding process, metal vaporizes in the molten pool, forming an elongated keyhole. A continuous and stable keyhole is crucial for achieving sufficient solder melting and minimizing weld defects. Key parameters for the keyhole are its depth and width. When the depth and width are too small, the molten pool formation rate is slow and component forming efficiency is low. When the depth and width are too large, the high-temperature liquid metal zone in the molten pool is excessive, resulting in a high temperature environment for grain growth, which reduces the component's size and shape accuracy.

[0003] Therefore, online monitoring of keyhole depth during laser welding is crucial. Currently, the primary method for keyhole depth monitoring is through a monitoring system based on optical low-coherence imaging. However, due to potential unknown errors or inaccuracies in the calibration process, the accuracy of keyhole depth information collected using optical low-coherence imaging is low, leading to ineffective keyhole depth monitoring. Therefore, evaluating the accuracy of keyhole depth information collected using optical low-coherence imaging is crucial. Summary of the Invention

[0004] The main purpose of this application is to provide a low-coherence imaging quality evaluation method, device and electronic equipment to evaluate the accuracy of key depth information collected by optical low-coherence imaging, providing a prerequisite for online monitoring of key depth during laser welding.

[0005] To achieve the above objectives, the present application provides a low-coherence imaging quality evaluation method, comprising:

[0006] Acquire point cloud data related to the keyhole during the laser welding process, and obtain a peripheral point cloud projection image of the keyhole based on the point cloud data;

[0007] performing a keyhole region fitting process multiple times to determine the keyhole region based on fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection image and a grid is divided according to a preset scale, and the fitting parameters of the keyhole region are determined based on grid parameters of each grid; the preset scale is different in different fitting processes;

[0008] An imaging quality evaluation result is determined based on the point cloud data within the keyhole region and the area of ​​the keyhole region.

[0009] Optionally, obtaining the peripheral point cloud projection map of the keyhole based on the point cloud data includes: segmenting the point cloud data using a preset segmentation formula to obtain a peripheral point cloud data set and a keyhole point cloud data set; projecting the peripheral point cloud data set to a preset welding surface to obtain the peripheral point cloud projection map.

[0010] Optionally, the preset segmentation formula is:

[0011]

[0012] Where, is the point cloud data of the jth point before segmentation, is the peripheral point cloud data set, is the keyhole point cloud data set, is the vertical distance between the jth point and the center point of the laser transmitter head, is the vertical distance from the center point of the laser emission head to the preset welding surface, is the preset distance threshold.

[0013] Optionally, the grid parameters include the number of point clouds in the grid, the grid area, and the distance between the grid and the central grid, where the central grid is the grid where the origin of the coordinate system is located; determining the fitting parameters of the keyhole area based on the grid parameters of each grid includes: for any grid, using a preset indicator formula and based on the number of point clouds in the grid, the grid area, and the distance between the grid and the central grid, determining a grid evaluation parameter; using a preset screening algorithm and based on the grid evaluation parameters of each grid, determining multiple target grids; and bringing the point cloud data of the center point of each target grid into a Hough transform algorithm to obtain the fitting parameters of the keyhole area.

[0014] Optionally, the method of determining a plurality of target grids by using a preset screening algorithm and based on grid evaluation parameters of each grid includes: sorting the grid evaluation parameters in descending order; selecting a grid evaluation parameter within a preset percentage interval from the side with a smaller grid evaluation parameter by using the preset screening algorithm, and using the grid corresponding to the selected grid evaluation parameter as the target grid.

[0015] Optionally, the preset indicator formula is:

[0016]

[0017] Where, is the grid evaluation parameter of the i-th grid, is the number of point clouds of the i-th grid, is the grid area of ​​the i-th grid, is the distance between the center point of the i-th grid and the center point of the central grid.

[0018] Optionally, the point cloud data within the keyhole area includes the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, and the coordinate data of each point; and determining the imaging quality evaluation result based on the point cloud data in the keyhole area and the area of ​​the keyhole area includes: using a preset quality evaluation formula and based on the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, the coordinate data of each point, the coordinate data of the center point of the keyhole area, and the area of ​​the keyhole area, to determine the imaging quality evaluation result.

[0019] Optionally, the preset quality evaluation formula is:

[0020]

[0021] Where, is the imaging quality evaluation result, is the area of ​​the keyhole region, is the number of point clouds in the keyhole area, is the signal strength of the zth point in the i-th grid in the keyhole area, is the total signal strength in the keyhole area, is the coordinate data of the zth point in the i-th grid in the keyhole area, is the coordinate data of the center point of the keyhole area.

[0022] In addition, to achieve the above-mentioned purpose, the present application also provides a low-coherence imaging quality evaluation device, including: an acquisition module, used to acquire point cloud data related to the keyhole during the laser welding process, and obtain a peripheral point cloud projection map of the keyhole based on the point cloud data; a fitting module, used to execute the keyhole area fitting process multiple times to determine the keyhole area based on the fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection map and the grid is divided according to a preset scale, and the fitting parameters of the keyhole area are determined based on the grid parameters of each grid; the preset scale is different in different fitting processes; an evaluation module is used to determine the imaging quality evaluation result based on the point cloud data in the keyhole area and the area of ​​the keyhole area.

[0023] The present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the low-coherence imaging quality evaluation method as described above is implemented.

[0024] The low-coherence imaging quality evaluation method of the present application obtains point cloud data related to the keyhole during the laser welding process, and obtains a peripheral point cloud projection map of the keyhole based on the point cloud data; then, the keyhole area fitting process is performed multiple times at different preset scales. During each fitting process, a coordinate system is constructed based on the peripheral point cloud projection map and a grid is divided according to the preset scale. The fitting parameters of the keyhole area are determined based on the grid parameters of each grid, and the keyhole area is fitted based on the fitting parameters obtained in each fitting process; finally, the imaging quality evaluation result is determined based on the point cloud data within the keyhole area and the area of ​​the keyhole area, thereby achieving an evaluation of the accuracy of key depth information collected by optical low-coherence imaging. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a schematic diagram of a laser welded keyhole according to a specific example of the present application;

[0026] Figure 2 This is one of the flow charts of the low coherence imaging quality evaluation method according to an embodiment of the present application;

[0027] Figure 3 This is the second flow chart of the low coherence imaging quality evaluation method according to an embodiment of the present application;

[0028] Figure 4 This is a keyhole-related point cloud distribution diagram of a specific example of this application;

[0029] Figure 5 It is a peripheral point cloud projection diagram of a specific example of this application;

[0030] Figure 6 This is the third flow chart of the low coherence imaging quality evaluation method according to an embodiment of the present application;

[0031] Figure 7 is a schematic diagram of grid division of a specific example of this application;

[0032] Figure 8 Schematic diagram of the structure of a low-coherence imaging quality evaluation device according to an embodiment of the present application;

[0033] Figure 9 An example of a physical structure diagram of an electronic device;

[0034] In the figure: 800, low coherence imaging quality evaluation device; 810, acquisition module; 820, fitting module; 830, evaluation module; 910, processor; 920, communication interface; 930, memory; 940, communication bus.

[0035] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0036] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0037] Laser welding involves bombarding the workpiece with a high-energy-density laser beam, melting the weld joint and forming a molten pool. Controlled parameters allow for the weld to be connected. Laser welding boasts low heat input, high speed, a large weld depth-to-width ratio, and a small heat-affected deformation zone. It is widely used in automotive manufacturing, electronics, aerospace, and other fields.

[0038] Figure 1 FIG. 1 is a schematic diagram of a laser welding keyhole according to a specific example of the present application. Figure 1 As shown in the figure, during laser welding, metal vaporizes to form an elongated keyhole in the liquid molten pool. A continuous and stable keyhole is crucial for achieving full solder melting and minimizing welding defects. Key parameters for a keyhole are its depth (the vertical distance from the keyhole surface to its deepest point) and width. When the width and depth are too small, the molten pool formation rate is slow, resulting in low component forming efficiency. When the width and depth are too large, the high-temperature liquid metal zone in the molten pool is excessive, creating a high temperature environment for grain growth, which reduces the component's size and shape accuracy.

[0039] Therefore, online monitoring of the keyhole depth during laser welding is crucial. Current keyhole depth monitoring systems primarily utilize optical low-coherence imaging. However, accurate keyhole depth monitoring using optical low-coherence imaging technology presupposes that the system can accurately and effectively capture keyhole information during welding. However, during this information collection process, incorrect welding process parameters, sensor installation errors, and low reflectivity of the welded object can lead to unreliable data, resulting in ineffective keyhole depth monitoring.

[0040] To this end, embodiments of the present application provide a low-coherence imaging quality evaluation method, device, and electronic device. This method converts point cloud data of the keyhole periphery during welding into a two-dimensional peripheral point cloud projection map, then fits the keyhole region based on the peripheral point cloud projection map to determine the keyhole region in optical low-coherence imaging. Finally, based on the point cloud data and area of ​​the keyhole region in the optical low-coherence imaging, the quality of the low-coherence imaging is evaluated to determine the quality of the optical low-coherence imaging. This method can serve as a basis for troubleshooting negative factors such as improper welding process parameter settings, large sensor installation errors, sensor mismatch, or low reflectivity of the weld object, thereby improving the reliability of online monitoring of keyhole depth in laser welding.

[0041] Figure 2 This is one of the flow charts of the low coherence imaging quality evaluation method of the embodiment of the present application, which can be executed by a processor in an optical low coherence imaging monitoring device. Figure 2 As shown, the low coherence imaging quality evaluation method may include the following steps:

[0042] Step 210: Acquire point cloud data related to the keyhole during the laser welding process, and obtain a peripheral point cloud projection map of the keyhole based on the point cloud data.

[0043] Step 220: Execute the keyhole region fitting process multiple times to determine the keyhole region based on the fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection map and a grid is divided according to a preset scale, and the fitting parameters of the keyhole region are determined based on the grid parameters of each grid; the preset scales are different in different fitting processes.

[0044] Step 230: Determine an imaging quality evaluation result based on the point cloud data within the keyhole region and the area of ​​the keyhole region.

[0045] It should be noted that the keyhole-related point cloud data may include point cloud data of the keyhole space and the welding plane space. In this embodiment, the positional relationship between the welding plane space and the keyhole space is represented in the form of a point cloud. Figure 1 The keyhole space marked in the figure, the welding plane space can be Figure 1 The space above the middle keyhole and below the laser launch head.

[0046] In this embodiment, the laser welding equipment can be parameterized and activated to begin welding on the test piece. The laser welding equipment can include a laser head, a water cooling system, a gas shielding system, a high-speed galvanometer, and the like. Specifically, manually set process parameters are input. The controller in the laser welding equipment controls the laser head to weld on the test piece based on the set process parameters. The set welding path can be a straight line, and the welding surface of the test piece is a horizontal plane.

[0047] During the welding process, metal vaporizes, forming a keyhole in the liquid molten pool. At this point, an optical low-coherence imaging monitoring device can be controlled to perform a three-dimensional scan of the keyhole surface. During the scan, the device records the interference signal generated by the mixture of reference light and the keyhole surface light. This interference signal reflects the intensity variation of the light reflected from the keyhole surface. Furthermore, a Fourier transform is performed on the collected interference signal to extract the frequency information of the light reflected from the keyhole surface, thereby calculating the depth information of the keyhole surface. Finally, based on the depth information of each measurement point and the scanning position, the three-dimensional coordinate data of the keyhole space and the weld plane space (i.e., the space surrounding the keyhole and the laser emission head) can be obtained. This three-dimensional coordinate data is then referred to as the point cloud data.

[0048] In this embodiment, the optical low-coherence imaging monitoring device continuously collects point cloud data related to the keyhole throughout the laser welding process, ultimately generating multiple sets of point cloud data. When evaluating the optical low-coherence imaging quality, any set of point cloud data can be selected from the multiple sets. Furthermore, after obtaining the keyhole-related point cloud data, the point cloud data can be visualized to generate a two-dimensional or three-dimensional point cloud image, making it easier for personnel to view the distribution of the point cloud data or facilitate subsequent processing of the point cloud data.

[0049] After obtaining the keyhole-related point cloud data, this point cloud data can be divided into the point cloud data of the keyhole space and the point cloud data of the keyhole periphery (i.e., the welding plane space). Furthermore, the point cloud data of the keyhole periphery can be projected onto the welding plane to obtain a peripheral point cloud projection map.

[0050] In step 220, after obtaining the peripheral point cloud projection map of the keyhole, the shape curve of the keyhole area can be fitted based on the peripheral point cloud projection map to obtain a mathematical equation that can be used to characterize the shape of the keyhole area, and then the keyhole area can be determined based on the fitted mathematical equation.

[0051] Specifically, a Cartesian coordinate system can be constructed on the peripheral point cloud projection map, and the origin of the coordinate system can be the projection point of the center point of the laser emitter. Meshing is performed on the peripheral point cloud projection map of the established coordinate system, and finally the fitting parameters of the keyhole area are determined based on the mesh parameters of each mesh.

[0052] It should be noted that the preset scale refers to the side length of a single grid cell. This scale can be set by personnel based on actual needs. The preset scale range can be 10% to 20% of the maximum width of the keyhole edge along the welding direction. For example, if the maximum width of the keyhole edge is 10 mm, the preset scale can be set to 1 x 1 mm. Furthermore, the fitting parameters of the keyhole region refer to the fitting equation used to characterize the keyhole region's outer contour, obtained by fitting the region's outer contour. The parameters of the fitting equation are the fitting parameters described in this application.

[0053] In the embodiment of the present application, after the keyhole area fitting process is completed once, a preset scale can be reset. , and according to the newly set preset scale Re-mesh the projection of the peripheral point cloud. After re-meshing at different preset scales, re-determine the fitting parameters for the keyhole region based on the mesh parameters of each grid. This process can be repeated repeatedly, with the preset scales changed multiple times, and the keyhole region fitting process repeated multiple times, to obtain multiple sets of fitting parameters. Finally, the optimal set of fitting parameters can be selected from these sets to serve as the fitting equation parameters for the keyhole region shape.

[0054] In step 230, after obtaining the fitting parameters for the keyhole region, a mathematical equation representing the shape of the keyhole region can be formed based on the fitting parameters. In this embodiment, after fitting the keyhole region and finding the keyhole region in the peripheral point cloud projection image, the optical low-coherence imaging quality evaluation result can be obtained based on the point cloud data falling within the keyhole region and the area of ​​the keyhole region.

[0055] Specifically, this embodiment primarily uses three parameters—point cloud density, point cloud signal strength, and central concentration—as evaluation indicators for optical low-coherence imaging quality. Therefore, the point cloud data for the keyhole region can include these three parameters. Finally, a pre-defined quality evaluation formula constructed based on these three parameters can be used to calculate an optical low-coherence imaging quality score, which can be used as the imaging quality evaluation result. If the point cloud density in the keyhole region is low, the point cloud signal strength is weak, or the point cloud central concentration is low, it can be assumed that the welding process parameters are improperly set, the sensor installation error is large, the sensor is not compatible, or the weld object has low reflectivity. In this case, the key depth information collected by the optical low-coherence imaging monitoring equipment is less accurate. Therefore, the operator can adjust the optical low-coherence imaging monitoring equipment and re-collect the key depth information.

[0056] Figure 3 This is the second flow chart of the low coherence imaging quality evaluation method according to an embodiment of the present application. Figure 3 As shown, in some embodiments, step 210 of obtaining a peripheral point cloud projection of the keyhole based on the point cloud data may include the following steps:

[0057] Step 310: Segment the point cloud data using a preset segmentation formula to obtain a peripheral point cloud data set and a keyhole point cloud data set.

[0058] Step 320: Project the peripheral point cloud data set onto the preset welding surface to obtain a peripheral point cloud projection map.

[0059] In the description of the aforementioned embodiment, the point cloud data related to the keyhole during the laser welding process obtained by the processor in the optical low-coherence imaging monitoring device mainly includes the point cloud data of the keyhole space and the point cloud data of the space surrounding the keyhole (i.e., the point cloud data of the welding plane space). Figure 4 This is a keyhole-related point cloud distribution diagram of a specific example of this application. Figure 1 and Figure 4 It can be seen that the point cloud data collected by the optical low-coherence imaging monitoring equipment is mainly distributed in the keyhole area and the area between the keyhole and the laser emitter, and the point clouds of these two areas can be clearly distinguished in space. The embodiment of the present application mainly realizes the segmentation of point cloud data by the coordinates of each point in the point cloud data, and obtains the peripheral point cloud dataset and the keyhole point cloud dataset.

[0060] Continue to refer Figure 4Specifically, a three-dimensional coordinate system can be established with the center point of the laser emitter as the origin O. The positive direction of the X-axis of the three-dimensional coordinate system is the welding direction of the current position, the positive direction of the Y-axis of the three-dimensional coordinate system is the direction toward the keyhole, and the positive direction of the Z-axis of the three-dimensional coordinate system can be any direction perpendicular to the plane formed by the X-axis and the Y-axis. The processor of the optical low-coherence imaging monitoring device can obtain the required point cloud data based on the three-dimensional coordinate system. The point cloud data includes the three-dimensional coordinates of all points in the point cloud. It should be noted here that the welding positions corresponding to different groups of point cloud data may be different. All welding positions can be connected from front to back to form the aforementioned welding path. The current position is the welding position corresponding to the currently selected group of point cloud data.

[0061] Further, from Figure 4 It can be seen from the figure that the peripheral point cloud ( Figure 4 The horizontal strip point cloud distribution at the top) and the keyhole point cloud ( Figure 4 The point cloud distribution of the inverted triangle located at the bottom can be distinguished from the Y value. Based on this, the embodiment of the present application can pre-construct a segmentation formula (i.e., a preset segmentation formula) to segment the point cloud data through the preset segmentation formula.

[0062] In some implementations, the preset segmentation formula may be:

[0063]

[0064] Where, is the point cloud data of the jth point before segmentation, is the peripheral point cloud data set, is the keyhole point cloud data set, is the vertical distance between the jth point and the center point of the laser transmitter head, It is the vertical distance from the center point of the laser transmitter to the preset welding surface. It should be noted that the preset welding surface can be defined as: the distance from the origin O is , and the plane whose normal vector is parallel to the Y axis; in addition, the preset distance threshold can be manually set by the staff according to actual needs, and the preset distance threshold is not limited here.

[0065] Therefore, the Y coordinate in the point cloud can be less than or equal to + The point cloud data corresponding to the point is divided into the peripheral point cloud data set, and the point cloud with Y coordinate greater than + The point cloud data corresponding to the points are segmented into the keyhole point cloud data set, realizing the segmentation of the point cloud data.

[0066] After obtaining the peripheral point cloud data set, the point cloud data in the peripheral point cloud data set can be projected onto the preset welding surface based on the three-dimensional coordinates of each point in the peripheral point cloud data set to obtain a peripheral point cloud projection diagram. Specifically, because the preset welding surface is a plane parallel to the plane formed by the X-axis and the Z-axis, in short, the Y values ​​of all points on the preset welding surface are the same. Therefore, the Y values ​​of all points in the peripheral point cloud data set can be removed or set to the Y values ​​corresponding to the preset welding surface. In this way, the three-dimensional coordinates of each point in the peripheral point cloud data set can be converted into two-dimensional coordinates to obtain the desired peripheral point cloud projection diagram.

[0067] Figure 5 This is a peripheral point cloud projection diagram of a specific example of this application. Figure 5 As shown in the projection image, the peripheral point cloud is shaped like an ellipse, with the center of the ellipse representing the keyhole. Therefore, the outline of the keyhole is also elliptical. When fitting the keyhole, the mathematical equation parameters obtained are also elliptical.

[0068] Figure 6 This is the third flow chart of the low coherence imaging quality evaluation method of the embodiment of the present application. Figure 6 As shown, in some embodiments, the grid parameters may include the number of point clouds in the grid, the grid area, and the distance between the grid and the central grid, where the central grid is the grid where the origin of the coordinate system is located; step 220 determines the fitting parameters of the keyhole area based on the grid parameters of each grid, which may include the following steps:

[0069] Step 610: For any grid, determine the grid evaluation parameters using a preset indicator formula based on the number of point clouds in the grid, the grid area, and the distance between the grid and the center grid.

[0070] Step 620: Determine a plurality of target grids using a preset screening algorithm and based on grid evaluation parameters of each grid.

[0071] Step 630: Submit the point cloud data of each target grid center point into the Hough transform algorithm to obtain the fitting parameters of the keyhole area.

[0072] In this embodiment, after the peripheral point cloud projection is obtained, the projection point of the laser transmitter center point (i.e., the center point of the peripheral point cloud) can be used as the origin O. proj Build an X proj Y proj Coordinate system (such as Figure 5 shown), based on X proj Y proj The coordinate system can obtain the two-dimensional coordinates of each point in the peripheral point cloud (X proj , Y proj). After the coordinate system is constructed, you can Divide the grid on the peripheral point cloud projection map, and make the center point of one of the grids coincide with the origin O proj Overlap, and the grid can be defined as the center grid.

[0073] Figure 7 This is a schematic diagram of the grid division of a specific example of this application, such as Figure 7 As shown, after the peripheral point cloud projection map is meshed, the points in the peripheral point cloud are distributed in each grid, the number of grid midpoints on the peripheral point cloud is large, and the number of grid midpoints in the middle of the peripheral point cloud and outside the peripheral point cloud is small.

[0074] Based on this, the number of point clouds in each grid can be determined according to the two-dimensional coordinates of each point, the coordinates of the grid center point, and the preset scale; the grid area can be directly calculated using the preset scale. If the preset scale is , then the grid area is The distance between the grid and the center grid can be calculated by the coordinates of the center point of the grid and the coordinates of the center point of the center grid.

[0075] Furthermore, after the grid is divided according to a preset scale, the grid evaluation parameters of the grid can be determined using a preset indicator formula based on the number of point clouds in the grid, the grid area, and the distance between the grid and the center grid. It should be noted that the grid evaluation parameter is a comprehensive evaluation indicator used to characterize the positional relationship between the grid and the keyhole area. The embodiment of the present application mainly determines the comprehensive evaluation indicator of the grid from two aspects: the point cloud density in the grid and the distance from the center grid. It can be understood that when the point cloud density in the grid is high and the distance from the center grid is far, it indicates that the grid may be at the position of the peripheral point cloud; when the point cloud density in the grid is low and the distance from the center grid is close, it indicates that the grid may be in the keyhole area. Therefore, the relative positional relationship between the grid and the keyhole area can be characterized by the two indicators of the point cloud density in the grid and the distance from the center grid.

[0076] Taking a single grid as an example, the number of point clouds within the grid, the grid area, and the distance between the grid and the center grid can be substituted into the preset indicator formula to obtain the grid evaluation parameters for the grid. Similarly, the grid evaluation parameters of all grids are calculated, and the target grid is then selected based on the grid evaluation parameters of all grids.

[0077] In some implementations, the preset indicator formula may be:

[0078]

[0079] Where, is the grid evaluation parameter of the i-th grid, is the number of point clouds of the i-th grid, is the grid area of ​​the i-th grid, is the distance between the center point of the i-th grid and the center point of the center grid. The smaller it is, the lower the point cloud density in the grid is and the closer it is to the center grid. A larger value indicates a denser grid and a greater distance from the center grid.

[0080] After obtaining the mesh evaluation parameters for all meshes, a preset screening algorithm can be used to identify multiple target meshes based on the mesh evaluation parameters of each mesh. It should be noted that the preset screening algorithm can be a percentage filter; the selected target meshes are primarily those located at the junction of the keyhole area and the surrounding area, i.e., the meshes where the keyhole area outline is located. By using the point cloud data within these target meshes, a mathematical equation representing the keyhole area outline can be better fitted, thereby more accurately determining the keyhole area.

[0081] In some embodiments, step 620 uses a preset screening algorithm and determines multiple target grids based on the grid evaluation parameters of each grid, which may include: sorting the grid evaluation parameters in descending order; using the preset screening algorithm to select grid evaluation parameters within a preset percentage range from the side with smaller grid evaluation parameters, and using the grid corresponding to the selected grid evaluation parameters as the target grid.

[0082] Specifically, all grid evaluation parameters can be sorted from largest to smallest, and then a percentage filtering method can be used to select grid evaluation parameters within a preset percentage interval from the smaller end of the grid evaluation parameters. It should be noted that after all grid evaluation parameters are sorted, the position of each grid evaluation parameter in this sequence can be expressed in the form of a percentage. In this embodiment, the preset percentage interval can be set to 8% to 12%. The preset percentage interval can be specifically set by the staff based on the specifications of the peripheral point cloud projection map and the distribution of the peripheral point cloud, and is not specifically limited here.

[0083] As an example, after sorting all grid evaluation parameters in descending order, the percentage filtering method can be used to select the grid evaluation parameters at the end of this sequence and in the range of 8% to 12%, and the grids corresponding to these grid evaluation parameters are determined as target grids. The target grids have relatively low place cloud density and are relatively closer to the central grid.

[0084] As another example, after all grid evaluation parameters are sorted in descending order, the percentage filtering method can be used to select the grid evaluation parameters that are ranked in the last 10% of this sequence, and the grids corresponding to these grid evaluation parameters are determined as target grids.

[0085] Furthermore, the point cloud data of each target grid center point is brought into the Hough transform algorithm to obtain the fitting parameters of the keyhole area. Since the keyhole area is elliptical from a bird's-eye view (such as Figure 7 As shown in Figure 2, the fitting curve is also an ellipse, and the fitting equation is an ellipse equation. Specifically, the point cloud data of each target grid center point can be randomly sampled to inversely solve the parameters of the ellipse equation and obtain a set of fitting parameters of the ellipse equation. The grid is re-divided at the preset scale and the above fitting parameter determination steps are repeated. Finally, n sets of fitting parameters for the elliptic equation are obtained. It should be noted that n is the number of iterations and can be set by the staff according to actual needs. The larger n is, the more accurate the fitting parameters for the keyhole region are.

[0086] For the n sets of fitting parameters obtained above, this embodiment can use hard voting to determine the optimal fitting parameters. The optimal fitting parameters form the elliptical equation used to characterize the keyhole region shape. The hard voting rule is: if none of the n sets of fitting parameters are consistent, the average is taken as the optimal fitting parameter; if multiple sets of fitting equation parameters are consistent, the mode result is taken as the optimal fitting parameter.

[0087] As an example, assuming that there are 99 groups of fitting parameters, among which the 2nd and 3rd groups of fitting parameters are consistent, the 30th, 31st, and 32nd groups of fitting parameters are consistent, and the 96th, 97th, 98th, and 99th groups of fitting parameters are consistent, then the 96th, 97th, 98th, and 99th groups of fitting parameters are selected as the majority results and used as the final keyhole area fitting parameters.

[0088] After the fitting parameters of the keyhole region are determined, the keyhole region can be determined according to the fitting equation, and the optical low-coherence imaging quality can be evaluated based on the relevant data of the fitted keyhole region.

[0089] In some embodiments, the point cloud data within the keyhole region may include the number of point clouds within the keyhole region, the signal strength of each point within the keyhole region, and the coordinate data of each point. Step 230, determining the imaging quality evaluation result based on the point cloud data within the keyhole region and the area of ​​the keyhole region, may include determining the imaging quality evaluation result using a preset quality evaluation formula based on the number of point clouds within the keyhole region, the signal strength of each point within the keyhole region, the coordinate data of each point, the coordinate data of the center point of the keyhole region, and the area of ​​the keyhole region.

[0090] This embodiment primarily evaluates the quality of optical low-coherence imaging in the keyhole region from three perspectives: point cloud density, signal strength, and central concentration. Point cloud density is the ratio of the number of keyhole region points in the peripheral point cloud projection to the keyhole region's area; point cloud signal strength is the strength of the signal returned to the optical low-coherence imaging monitoring device; and central concentration is the degree of dispersion between the point cloud data and the center point of the fitted region.

[0091] It can be understood that the greater the point cloud density in the keyhole area, the stronger the point cloud signal intensity, or the higher the concentration of the point cloud center, the higher the quality of the collected point cloud data and the higher the quality of the optical low-coherence imaging.

[0092] Based on this, in some embodiments, the following preset quality evaluation formula can be constructed to achieve quantitative evaluation of optical low-coherence imaging quality:

[0093]

[0094] Where, is the imaging quality evaluation result, is the area of ​​the keyhole region, is the number of point clouds in the keyhole area, is the signal strength of the zth point in the i-th grid in the keyhole area, is the total signal strength in the keyhole area, is the coordinate data of the zth point in the i-th grid in the keyhole area, is the coordinate data of the center point of the keyhole area, Indicates the sum of the distances between the point cloud in the fitting area and the center point of the fitting area. as well as All are X proj O proj Y proj Coordinate data in the coordinate system.

[0095] In this embodiment, the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, the coordinate data of each point, the coordinate data of the center point of the keyhole area, and the area of ​​the keyhole area can be substituted into the above-mentioned preset quality evaluation formula to obtain the imaging quality evaluation result. , The smaller it is, the lower the quality of low-coherence imaging is. The larger the value, the higher the low-coherence imaging quality.

[0096] Therefore, the quantitative evaluation of optical low coherence imaging quality can be achieved, and the imaging quality evaluation results The level of directly reflects the quality of imaging, which improves the accuracy of online monitoring of the keyhole depth in laser welding. Secondly, the grid evaluation parameters of the grid are calculated based on the point cloud density of the grid in the keyhole area and the distance between the grid and the center grid. Then, the percentage filtering method is used to screen out the target grid with relatively low point cloud density and relatively close distance to the center grid. The center point of the selected target grid is substituted into the Hough transform to obtain the fitting equation of the keyhole area, which can greatly improve the computational efficiency of the Hough transform and realize the rapid determination of the laser welding keyhole position. Finally, the obtained imaging quality evaluation results can be used as a basis for troubleshooting negative factors such as improper welding process parameter settings, large sensor installation errors, sensor mismatch or low reflectivity of the welding object, thereby improving the credibility of online monitoring of the keyhole depth in laser welding.

[0097] Based on the above embodiments, an embodiment of the present application further provides a low coherence imaging quality evaluation device. Figure 8 FIG. 1 is a schematic structural diagram of a low-coherence imaging quality evaluation device according to an embodiment of the present application. Figure 8 As shown, the low coherence imaging quality evaluation device 800 may include an acquisition module 810 , a fitting module 820 and an evaluation module 830 .

[0098] Among them, the acquisition module 810 is used to obtain point cloud data related to the keyhole during the laser welding process, and obtain a peripheral point cloud projection map of the keyhole based on the point cloud data; the fitting module 820 is used to execute the keyhole area fitting process multiple times to determine the keyhole area based on the fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection map and a grid is divided according to a preset scale, and the fitting parameters of the keyhole area are determined based on the grid parameters of each grid; the preset scales are different in different fitting processes; the evaluation module 830 is used to determine the imaging quality evaluation result based on the point cloud data in the keyhole area and the regional area of ​​the keyhole area.

[0099] Thus, the acquisition module 810 acquires point cloud data related to the keyhole during the laser welding process, and obtains a peripheral point cloud projection map of the keyhole based on the point cloud data. The fitting module 820 then performs the keyhole region fitting process multiple times at different preset scales. During each fitting process, a coordinate system is constructed based on the peripheral point cloud projection map and a grid is divided according to the preset scale. The fitting parameters of the keyhole region are determined based on the grid parameters of each grid, and the keyhole region is then fitted based on the fitting parameters obtained in each fitting process. Finally, the evaluation module 830 determines an imaging quality evaluation result based on the point cloud data within the keyhole region and the regional area of ​​the keyhole region, thereby achieving an evaluation of the accuracy of key depth information collected by optical low-coherence imaging.

[0100] In some embodiments, the acquisition module 810 is specifically used to: segment the point cloud data using a preset segmentation formula to obtain a peripheral point cloud data set and a keyhole point cloud data set; project the peripheral point cloud data set to a preset welding surface to obtain a peripheral point cloud projection map.

[0101] In some implementations, the preset segmentation formula is:

[0102]

[0103] Where, is the point cloud data of the jth point before segmentation, is the peripheral point cloud data set, is the keyhole point cloud data set, is the vertical distance between the jth point and the center point of the laser transmitter head, It is the vertical distance from the center point of the laser transmitter to the preset welding surface. is the preset distance threshold.

[0104] In some embodiments, the grid parameters include the number of point clouds within the grid, the grid area, and the distance between the grid and the central grid, where the central grid is the grid where the origin of the coordinate system is located; the fitting module 820 is specifically used to: for any grid, use a preset indicator formula and determine the grid evaluation parameters based on the number of point clouds within the grid, the grid area, and the distance between the grid and the central grid; use a preset screening algorithm and based on the grid evaluation parameters of each grid to determine multiple target grids; and bring the point cloud data of the center point of each target grid into the Hough transform algorithm to obtain the fitting parameters of the keyhole area.

[0105] In some embodiments, the fitting module 820 is further specifically used to: sort the grid evaluation parameters in descending order; select the grid evaluation parameters within a preset percentage interval from the side with the smaller grid evaluation parameters using a preset screening algorithm, and use the grid corresponding to the selected grid evaluation parameters as the target grid.

[0106] In some embodiments, the preset indicator formula is:

[0107]

[0108] Where, is the grid evaluation parameter of the i-th grid, is the number of point clouds of the i-th grid, is the grid area of ​​the i-th grid, is the distance between the center point of the i-th grid and the center point of the center grid.

[0109] In some embodiments, the point cloud data within the keyhole area includes the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, and the coordinate data of each point; the evaluation module 830 is specifically used to: use a preset quality evaluation formula and determine the imaging quality evaluation result based on the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, the coordinate data of each point, the coordinate data of the center point of the keyhole area, and the area of ​​the keyhole area.

[0110] In some embodiments, the preset quality evaluation formula is:

[0111]

[0112] Where, is the imaging quality evaluation result, is the area of ​​the keyhole region, is the number of point clouds in the keyhole area, is the signal strength of the zth point in the i-th grid in the keyhole area, is the total signal strength in the keyhole area, is the coordinate data of the zth point in the i-th grid in the keyhole area, The coordinate data of the center point of the keyhole area.

[0113] It should be noted that for details not disclosed in the low coherence imaging quality evaluation device of this embodiment, please refer to the details disclosed in the embodiment of the low coherence imaging quality evaluation method in the embodiment of this specification, and will not be repeated here.

[0114] Based on the above embodiments, Figure 9 An example of a physical structure diagram of an electronic device is shown below. Figure 9 As shown, the electronic device may include: a processor 910, a communications interface 920, a memory 930, and a communications bus 940, wherein the processor 910, the communications interface 920, and the memory 930 communicate with each other via the communications bus 940. The processor 910 may call logic instructions in the memory 930 to execute a low-coherence imaging quality assessment method, which includes: acquiring point cloud data related to a keyhole during a laser welding process, and obtaining a peripheral point cloud projection map of the keyhole based on the point cloud data; performing a keyhole region fitting process multiple times to determine the keyhole region based on fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection map and grids are divided according to a preset scale, and fitting parameters of the keyhole region are determined based on grid parameters of each grid; the preset scales are different in different fitting processes; and an imaging quality assessment result is determined based on the point cloud data within the keyhole region and the area of ​​the keyhole region.

[0115] Furthermore, the logic instructions in the aforementioned memory 930 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0116] On the basis of the above embodiments, on the other hand, the present invention further provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the low-coherence imaging quality evaluation method provided by the above methods, the method including: acquiring point cloud data related to the keyhole during the laser welding process, and obtaining a peripheral point cloud projection map of the keyhole based on the point cloud data; performing a keyhole area fitting process multiple times to determine the keyhole area based on the fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection map and a grid is divided according to a preset scale, and the fitting parameters of the keyhole area are determined based on the grid parameters of each grid; the preset scales are different in different fitting processes; and the imaging quality evaluation result is determined based on the point cloud data in the keyhole area and the area of ​​the keyhole area.

[0117] On the basis of the above embodiments, in another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the low-coherence imaging quality evaluation method provided by the above methods, the method comprising: acquiring point cloud data related to the keyhole during the laser welding process, and obtaining a peripheral point cloud projection map of the keyhole based on the point cloud data; performing a keyhole area fitting process multiple times to determine the keyhole area based on the fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection map and a grid is divided according to a preset scale, and the fitting parameters of the keyhole area are determined based on the grid parameters of each grid; the preset scales are different in different fitting processes; and an imaging quality evaluation result is determined based on the point cloud data in the keyhole area and the area of ​​the keyhole area.

[0118] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0119] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

Claims

1. A low coherence imaging quality evaluation method, characterized in that: include: Acquire point cloud data related to the keyhole during laser welding, and obtain a peripheral point cloud projection image of the keyhole based on the point cloud data; performing a keyhole region fitting process multiple times to determine the keyhole region based on fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection image and a grid is divided according to a preset scale, and the fitting parameters of the keyhole region are determined based on grid parameters of each grid; the preset scale is different in different fitting processes; Determine an imaging quality evaluation result based on the point cloud data within the keyhole region and the area of ​​the keyhole region; The grid parameters include the number of point clouds in the grid, the grid area, and the distance between the grid and the central grid, where the central grid is the grid where the origin of the coordinate system is located. The step of determining the fitting parameters of the keyhole area based on the grid parameters of each grid includes: For any grid, determining a grid evaluation parameter using a preset indicator formula based on the number of point clouds in the grid, the area of ​​the grid, and the distance between the grid and the central grid; Determining a plurality of target grids using a preset screening algorithm and based on grid evaluation parameters of each of the grids; Substituting the point cloud data of the center point of each target grid into the Hough transform algorithm to obtain the fitting parameters of the keyhole area; The point cloud data within the keyhole area includes the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, and the coordinate data of each point; and determining the imaging quality evaluation result based on the point cloud data in the keyhole area and the area of ​​the keyhole area includes: Determining the imaging quality evaluation result using a preset quality evaluation formula and based on the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, the coordinate data of each point, the coordinate data of the center point of the keyhole area, and the area of ​​the keyhole area; The preset quality evaluation formula is: Where, is the imaging quality evaluation result, is the area of ​​the keyhole region, is the number of point clouds in the keyhole area, is the signal strength of the zth point in the i-th grid in the keyhole area, is the total signal strength in the keyhole area, is the coordinate data of the zth point in the i-th grid in the keyhole area, is the coordinate data of the center point of the keyhole area.

2. The low coherence imaging quality evaluation method according to claim 1, characterized in that: The step of obtaining a peripheral point cloud projection image of the keyhole based on the point cloud data includes: Segmenting the point cloud data using a preset segmentation formula to obtain a peripheral point cloud data set and a keyhole point cloud data set; The peripheral point cloud data set is projected onto a preset welding surface to obtain the peripheral point cloud projection map.

3. The low coherence imaging quality evaluation method according to claim 2, characterized in that: The preset segmentation formula is: Where, is the point cloud data of the jth point before segmentation, is the peripheral point cloud data set, is the keyhole point cloud data set, is the vertical distance between the jth point and the center point of the laser transmitter head, is the vertical distance from the center point of the laser emission head to the preset welding surface, is the preset distance threshold.

4. The low coherence imaging quality evaluation method according to claim 1, characterized in that: The method of determining a plurality of target grids by using a preset screening algorithm and based on grid evaluation parameters of each grid comprises: Sorting the grid evaluation parameters in descending order; The preset screening algorithm is used to select a grid evaluation parameter within a preset percentage interval from the side where the grid evaluation parameter is the smallest, and the grid corresponding to the selected grid evaluation parameter is used as the target grid.

5. The low coherence imaging quality evaluation method according to claim 1, characterized in that: The preset indicator formula is: Where, is the grid evaluation parameter of the i-th grid, is the number of point clouds of the i-th grid, is the grid area of ​​the i-th grid, is the distance between the center point of the i-th grid and the center point of the central grid.

6. A low coherence imaging quality evaluation device, characterized in that: include: an acquisition module, configured to acquire point cloud data related to the keyhole during laser welding, and obtain a peripheral point cloud projection image of the keyhole based on the point cloud data; a fitting module, configured to execute a keyhole region fitting process multiple times to determine the keyhole region based on fitting parameters obtained in each fitting process; wherein, in each fitting process, a coordinate system is constructed based on the peripheral point cloud projection image and a grid is divided according to a preset scale, and the fitting parameters of the keyhole region are determined based on grid parameters of each grid; the preset scale is different in different fitting processes; An evaluation module, configured to determine an imaging quality evaluation result based on the point cloud data within the keyhole region and the area of ​​the keyhole region; The grid parameters include the number of point clouds within the grid, the grid area, and the distance between the grid and the central grid, where the central grid is the grid where the origin of the coordinate system is located; the fitting module is specifically configured to determine, for any grid, a grid evaluation parameter using a preset indicator formula based on the number of point clouds within the grid, the grid area, and the distance between the grid and the central grid; determine multiple target grids using a preset screening algorithm based on the grid evaluation parameters of each of the grids; and substitute the point cloud data of the center point of each of the target grids into a Hough transform algorithm to obtain fitting parameters for the keyhole region; The point cloud data within the keyhole area includes the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, and the coordinate data of each point; the evaluation module is specifically configured to determine the imaging quality evaluation result using a preset quality evaluation formula and based on the number of point clouds in the keyhole area, the signal strength of each point in the keyhole area, the coordinate data of each point, the coordinate data of the center point of the keyhole area, and the area of ​​the keyhole area; The preset quality evaluation formula is: Where, is the imaging quality evaluation result, is the area of ​​the keyhole region, is the number of point clouds in the keyhole area, is the signal strength of the zth point in the i-th grid in the keyhole area, is the total signal strength in the keyhole area, is the coordinate data of the zth point in the i-th grid in the keyhole area, is the coordinate data of the center point of the keyhole area.

7. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the low-coherence imaging quality evaluation method according to any one of claims 1 to 5 is implemented.

Images